V.M. Grinyak1, K.S. Shutov2, A.S. Devyatisilnyi3, A.V. Artemyev4
1 Vladivostok State University (Vladivostok, Russia)
2 Far Eastern Federal University (Vladivostok, Russia)
3 Institute of Automation and Control Processes FEBRAS (Vladivostok, Russia)
4 Maritime State University named after admiral G.I. Nevelskoy (Vladivostok, Russia)

1 victor.grinyak@gmail.com, 2 con.shutoff@yandex.ru, 3 devyatis@iacp.dvo.ru, 4 artemyev@msun.ru

The article is devoted to the problem of controlling the movement of an unmanned device along a program trajectory set by a sequence of points. Such movement, which involves bypassing points, is characterized by a variety of possible trajectories. In classical control theory, the choice of a specific trajectory is associated with solving an optimization problem. At the same time, on the one hand, the formulation of criteria for such optimization is a problem, and, on the other hand, in problems of movement along a program trajectory, it is typically not necessary to find mathematically optimal solutions, but rather, solutions that are suitable for a particular practical case.

The goal of the article is to develop a motion control system based on a program trajectory that operates according to the «similarity criterion», aiming to make the device's movement in automatic mode resemble that of a human-controlled device. The tool for implementing such a control system is a neural network trained on simulated or real motion data.

The paper proposes a software and architectural solution for a motion control system based on the separation of command generation and command execution subsystems. The interaction between subsystems is managed through a message queue. The solution offers modularity and flexibility, allowing for easy adaptation and customization of individual components within the system. A model of the motion control problem has been developed, using the example of an unmanned vehicle-type device. A neural network configuration has been proposed for generating control commands, and a method has been suggested for training it using data received from a operator or generated as a result of simulation. Several examples of neural network training that lead to different device movements have been considered. These examples demonstrate that the system can adapt to various conditions and provide a level of control as close as possible to that of a human.

The proposed approach to motion control could be used to develop control systems for various types of unmanned devices, ranging from ground vehicles to aerial and aquatic drones. These control systems can be applied in the automotive industry, logistics, agriculture, and other fields where different control modes are required.

Grinyak V.M., Shutov K.S., Devyatisilnyi A.S., Artemyev A.V. Autonomous vehicle motion control along a program trajectory based on machine learning. Neurocomputers. 2025. V. 27. № 1. P. 66–76. DOI: https://doi.org/10.18127/j19998554-202501-06 (in Russian)

1. Lapshinov S.A., Shakhnov V.A., Yudin A.V. Napravleniya intellektualizatsii upravleniya dvizheniem mobil'nogo robota. Nejrokomp'yutery: razrabotka, primenenie. 2021. T. 23. № 1. S. 50–62. DOI: 10.18127/j19998554202101-06. (in Russian)
2. Petushkov A.M., Samokhvalov O.A. Metodicheskij podkhod k povysheniyu effektivnosti monitoringa zon chrezvychajnykh situatsij bol'shoj ploshchadi gruppoj avtonomnykh bespilotnykh letatel'nykh apparatov. Naukoemkie tekhnologii. 2022. T. 23. № 1. S. 35–41. DOI: 10.18127/j19998465-202201-05. (in Russian)
3. Nguen K.T., Vu A.Kh., Yagodkina T.V. Zadacha sovmeshchennogo upravleniya BLA v usloviyakh mnogofaktornoj neopredelennosti. Radiotekhnika. 2020. T. 84. № 1 (2). S. 55–61. DOI: 10.18127/j00338486-202001(02)-06. (in Russian)
4. Khrustalev M.M., Khalina A.S. Identifikatory ponizhennoj razmernosti v zadache stabilizatsii bespilotnogo letatel'nogo apparata v nespokojnoj atmosfere. Trudy MAI. 2018. № 102. S. 22. (in Russian)
5. Kikin I.S. Algoritm upravleniya traektoriej vyvoda letatel'nogo apparata v zadannuyu tochku s zadannym traektornym uglom. Vestnik komp'yuternykh i informatsionnykh tekhnologij. 2017. № 12 (162). S. 3–11. DOI: 10.14489/vkit.2017.12.pp.003-011. (in Russian)
6. Shestakov E.I., Zhdanov A.A. Upravlenie modul'nym manipulyatsionnym robotom na osnove metoda avtonomnogo adaptivnogo upravleniya. Nejrokomp'yutery: razrabotka, primenenie. 2022. T. 24. № 6. S. 38–45. DOI: 10.18127/j19998554-202206-04. (in Russian)
7. Xiao X., Liu Bo., Warnell G., Stone P. Motion planning and control for mobile robot navigation using machine learning: a survey. Autonomous Robots. 2022. V. 46. № 5. P. 569–597. DOI: 10.1007/s10514-022-10039-8.
8. Gong J., Gong C., Lin Y., Li Z., Lu C. Review on machine learning methods for motion planning and control policy of intelligent vehicles. Transactions of Beijing institute of Technology. 2022. V. 42. № 7. P. 665–674. DOI: 10.15918/j.tbit1001-0645.2022.095.
9. Grinyak V.M., Devyatisil'nyj A.S., Lyul'ko V.I., Tsybanov P.A. Vozmozhnosti pozitsionirovaniya vnutri pomeshchenij s pomoshch'yu bluetooth ustrojstv. Modelirovanie, optimizatsiya i informatsionnye tekhnologii. 2018. T. 6. № 2 (21). S. 132–143. (in Russian)
10. Yang S.H., Jeong E.M., Kim D.R., Kim H.S., Son Y.H., Han S.K. Indoor three-dimensional location estimation based on LED visible light communication. Electronics Letters. 2013. V. 49. № 1. P. 54–56. DOI: 10.1049/el.2012.3167.
11. Thomas A.J., Petridis M., Walters S.D., Gheytassi S.M., Morgan R.E. Two hidden layers are usually better than one. Engineering applications of neural networks. Communications in Computer and Information Science. 2017. V. 744. P. 279–290. DOI: 10.1007/978-3-319-65172-9_24.
12. Chu Y., Fei J., Hou S. Adaptive global sliding-mode control for dynamic systems using double hidden layer recurrent neural network structure. IEEE Transactions on Neural Networks and Learning Systems. 2020. V. 31. № 4. P. 1297–1309. DOI: 10.1109/TNNLS.2019. 2919676.
13. Jia C., Kong D., Du L. Recursive terminal sliding-mode control method for nonlinear system based on double hidden layer fuzzy emotional recurrent neural network. IEEE Access. 2022. V. 10. P. 118012–118023. DOI: 10.1109/ACCESS.2022.3220800.
14. Artem'ev B.V., Vlasov A.I., Isroilov Zh.O., Mulatola S. Analiz programmnykh bibliotek dlya razrabotki vstraivaemykh nejrosetevykh prilozhenij. Nejrokomp'yutery: razrabotka, primenenie. 2023. T. 25. № 6. S. 5–12. DOI: 10.18127/j19998554-202306-01. (in Russian)